Expose hidden threats
—with powerful, precise, AI-powered threat detection
for security screening systems.
Automated Next Generation Threat Detection
EyeFox is a revolutionary AI-based system that delivers automated, immediate threat detection at high-accuracy levels for X-ray security screening operators.
EyeFox provides unrelenting and focused analysis, rapidly distinguishing threats from other items in real-time. This minimizes close contact with bag contents and people, increasing efficiency and throughput.
CT & X-ray Threat Detection
EyeFox’s revolutionary technology and product design quickly adjust to new threats as they arise.
Developed Based on Diverse Real Threats
EyeFox is fed with hundreds of thousands of real threat images from our R&D and partner-generated databases.
Multiple Market Applications
- Aviation & Mass Transportation
- Law Enforcement
- Event Security
- Government Buildings
- Maritime Security
- Border Control
- Critical Infrastructure Installation
- Mail Screening
- Cargo Security
- Sub-seconds detection time
- Maximizes throughput
- Minimizes false alarm rates
- Constantly improving algorithms
- Increases detection accuracy
- Lowers operational cost
Low Threat Detection Rates
Image interpretation relies heavily on human perception and decision-making. Failure rates and false alarms are high, due to the disruptive environment and other external variables such as the pressure to perform or tiredness. Majority of the scanned bags do not contain threats, which can result in complacency as time passes. While many actual threats are missed because of image complexity and the difficulty posed by the object’s viewing angle, the list of prohibited items continues to grow, challenging the human operator even more.
Long and slow-moving queues to security screening frustrate airline passengers. Separating electronics and liquids prior to screening helps the image interpretation task, but increases the time passengers spend at the checkpoint. In addition, up to 30% of the bags are flagged for manual inspection, prolonging the process further. Allowing passengers to keep electronics and liquids inside their bags and reducing the number of items erroneously flagged for manual search, would dramatically increase throughput.
The EyeFox Solution
EyeFox detects and identifies hidden threats. Our solution employs deep learning computer vision to the screening process for automatic threat detection. Also, it creates a centralised image processing network whose value increases exponentially as it develops, learns, and improves with data aggregation.
AI systems replicate the capabilities of the human mind.
These advanced algorithms can sort large amounts of visual data, which in the security X-ray screening realm make decisions on whether to reject or clear a passenger bag in the presence of a detected threat item.
Machine learning plays a key role in the AI technology we use, where a computer system is fed large amounts of data, which it then uses to learn how to carry out a specific task.
A subfield of machine learning is deep learning, where neural networks are expanded into sprawling networks with a huge number of layers that are trained using massive amounts of data. It is these deep neural networks that have fueled the current leap forward in the ability of computers to carry out tasks like computer vision.
In our data production and testing center, we have created a vast data set with over 3 million images of threat and non-threat items to teach our detection algorithm and reduce false alarms. It is constantly updated with new images and orientations; operating on a wide variety of X-ray systems.Contact us to learn more!
Publications & NewsView all
Neural Guard produces automated threat detection solutions powered by AI for the security screening market. With the expansion of global trends like urbanization, aviation, mass transportation, and global trade, the associated security and commercial challenges have become ever more crucial.Read more
In this blog post, we explored a data creation method that is the opposite of traditional methods — building your test-set first, then deriving the train-set from it. We explain why for companies doing deep learning, it is a great method to deal with the data acquisition costs.Read more